Search research articles

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Deep Learning of Histopathology Predicts Outcomes After Surgery for Pancreatic Cancer.

JCO clinical cancer informatics·2026

Same author

Sparse Non-Local CRF With Applications.

IEEE transactions on pattern analysis and machine intelligence·2024

Same author

Machine learning in computational histopathology: Challenges and opportunities.

Genes, chromosomes & cancer·2023

Same author

Efficient Graph Cut Optimization for Full CRFs with Quantized Edges.

IEEE transactions on pattern analysis and machine intelligence·2019

Same author

Convexity Shape Prior for Binary Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2017

Same author

Local Submodularization for Binary Pairwise Energies.

IEEE transactions on pattern analysis and machine intelligence·2016

Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026

查看所有相关文章

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

Search research articles

相关实验视频

Updated: Jun 29, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

用超参数估计对弱监督的单一类细分进行规范化损失.

Zongliang Ji, Olga Veksler

IEEE transactions on pattern analysis and machine intelligence

|April 3, 2024

概括

此摘要是机器生成的。

本研究引入了一种新的弱监督细分方法,使用受条件随机场 (CRF) 启发的规范损失函数. 这种方法避免了像素级的注释,并在各种细分任务中取得了最先进的结果.

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

相关实验视频

Last Updated: Jun 29, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

科学领域:

计算机视觉计算机视觉
机器学习机器学习
人工智能的人工智能

背景情况:

图像细分通常需要精确的像素级注释,这是劳动密集型和昂贵的.
现有的弱监督的方法经常与复杂的对象属性作斗争,并且缺乏跨不同数据集的概括性.

研究的目的:

开发一种图像级弱监督细分方法,绕过像素精确注释的需求.
引入基于条件随机场 (CRF) 建模的新型规范损失函数,用于指导卷积神经网络 (CNN).
为了实现适用于各种任务和数据集的统一和可适应的细分方法.

主要方法:

提出了一种由经典的条件随机场 (CRF) 建模所启发的规范化损失函数.
一个回火算法被开发出来,以促进CNN的训练与规范化损失.
介绍了超参数设置的方法,解决了缺乏像素精确基准真理的挑战.

主要成果:

拟议的方法成功地引导CNN在没有像素级监督的情况下实现准确的对象细分.
在突出的对象细分,共同细分和多类语义细分任务中取得了最先进的结果.
该方法在使用标准CNN架构的不同细分任务和数据集中表现出有效性.

结论:

开发的图像级弱监督细分方法为像素级注释提供了一个有效的替代方案.
受CRF启发的规范化损失函数和回火算法为细分提供了强大的和可通用的解决方案.
这项工作推进了计算机视觉中的弱监督学习领域,在减少注释努力的情况下实现了竞争性表现.